© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 53496
    Prev
    Next
    INDEX
    Explanations

    Thomas/th

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lsa
    -0.28
     Cy
    -0.27
    lations
    -0.27
    ushman
    -0.26
     lng
    -0.26
    tings
    -0.26
    lng
    -0.25
    æľĹ
    -0.25
    arl
    -0.25
    lm
    -0.25
    POSITIVE LOGITS
    bron
    0.26
    éĻĦå±ŀ
    0.25
    [mid
    0.24
    ENA
    0.24
    ena
    0.24
    amps
    0.24
    erek
    0.24
    驸
    0.24
     master
    0.24
    itten
    0.23
    Activations Density 0.008%

    No Known Activations